ReLTEx: Reliable LLM-based Taxonomy Expansion

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Zeinab Ghamlouch, Mehwish Alam
• Venue: arXiv: cs.CL
• Published: 2026-08-11
• Collected: 2026-08-12
• URL: http://arxiv.org/abs/2608.10970v1
• PDF: https://arxiv.org/pdf/2608.10970v1
• DOI: UNKNOWN
• Registry group: academic_apis_and_preprints
• Evidence role: canonical_academic_index
• Language: en
• Country / region: UNKNOWN

Plain-Language Brief

The paper discusses a new framework called ReLTEx for improving the reliability of Large Language Model (LLM)-based taxonomy expansion. The framework combines LLM-driven candidate generation with structure-aware validation and recursive expansion control to reduce hallucinations, resulting in more reliable and semantically coherent expansions.

What the Document Says

• Recent advances in Large Language Models have shown strong capabilities in generating semantically relevant concepts and relations.
• LLM-generated expansions can lead to noisy, redundant, or hierarchically inconsistent structures, limiting their reliability for automated taxonomy expansion.
• The paper introduces ReLTEx, a framework for reliable LLM-based taxonomy expansion.
• ReLTEx combines LLM-driven candidate generation with structure-aware validation and recursive expansion control.
• These methods are intended to improve the consistency and quality of generated taxonomies by reducing hallucinations.
• The authors evaluate the proposed framework using benchmark taxonomies under a masked taxonomy expansion setting.
• They compare multiple validation strategies.
• Experimental results, supported by both adapted evaluation metrics and human evaluation, show that ReLTEx produces more reliable and semantically coherent taxonomy expansions.

Key Concepts Mentioned

• Large Language Models (LLMs)
• taxonomy enrichment
• reliability
• hallucinations
• evaluation metrics

Claims Made by the Document

• LLM-generated expansions can lead to noisy, redundant, or hierarchically inconsistent structures.
• ReLTEx improves the consistency and quality of generated taxonomies by reducing hallucinations.
• ReLTEx produces more reliable and semantically coherent taxonomy expansions.

Evidence Used

• The text mentions that LLM-generated expansions can lead to noisy, redundant, or hierarchically inconsistent structures.
• The paper states that ReLTEx combines certain methods to improve the consistency and quality of generated taxonomies.
• The authors present experimental results showing that ReLTEx produces more reliable and semantically coherent expansions.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

Recent advances in Large Language Models (LLMs) have demonstrated strong capabilities in generating semantically relevant concepts and relations, making them promising tools for taxonomy enrichment. However, directly relying on LLM-generated expansions often leads to noisy, redundant, or hierarchically inconsistent structures, limiting their reliability for automated taxonomy expansion. In this paper, we present ReLTEx, a framework for reliable LLM-based taxonomy expansion. ReLTEx combines LLM-driven candidate generation with structure-aware validation and recursive expansion control to improve the consistency and quality of generated taxonomies by reducing hallucinations. We evaluate the proposed framework using benchmark taxonomies under a masked taxonomy expansion setting and compare multiple validation strategies. Experimental results, supported by both adapted evaluation metrics and human evaluation, demonstrate that ReLTEx produces more reliable and semantically coherent taxonomy expansions.